cold-email

cold-email is a skill for Claude Code from Doris-Labs/sales-skills. It costs 65 tokens per session (1,467 once invoked), scanned A, original, MIT.

A guide for writing a short first-contact email to a potential customer who does not know you.

In plain words
What is it for?
It helps create outreach using a timely reason for contacting someone, a relevant proof point, and one low-effort question.
Why use it?
It keeps the message focused on one relevant problem and a simple reply, instead of sending a broad product pitch.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the sales-skills plugin — 30 skills shipped together

Good fit It helps create outreach using a timely reason for contacting someone, a relevant proof point, and one low-effort question.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/doris-labs/sales-skills/cold-email
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add Doris-Labs/sales-skills --skill cold-email
Clone the repo
git clone --depth 1 https://github.com/Doris-Labs/sales-skills

Made for: Claude Code.

Or install sales-skills, the plugin that ships this one along with the rest of its 30 skills.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for cold-email

README.md
[![agentmods](https://agentmods.dev/badge/skills/doris-labs/sales-skills/cold-email/github.svg)](https://agentmods.dev/skills/doris-labs/sales-skills/cold-email)
Your own site
<a href="https://agentmods.dev/skills/doris-labs/sales-skills/cold-email"><img src="https://agentmods.dev/badge/skills/doris-labs/sales-skills/cold-email/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for cold-email

Your own site · 80×15
<a href="https://agentmods.dev/skills/doris-labs/sales-skills/cold-email"><img src="https://agentmods.dev/badge/skills/doris-labs/sales-skills/cold-email.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 65 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,467 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00065 $0.01467
Opus 5 $0.00032 $0.00733
Sonnet 5 $0.00013 $0.00293
Haiku 4.5 $0.00006 $0.00147

Measured 12d ago against content hash 06a70c0fb571, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

cold-email scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/cold-email/SKILL.md · 150 lines

How it starts

The opening of the file, as written. The whole thing — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Cold Email

Purpose

Write a first-touch email a busy stranger actually replies to: one problem, one relevance hook grounded in a real trigger, and one low-friction ask — not a pitch.

Inputs

  • Who you're emailing (name, role, company)
  • A real trigger or reason-to-reach-out-now (hire, funding, launch, post, mutual context)
  • The one problem you solve for this persona
  • A proof point you can cite (a similar customer, a result, a relevant pattern)

Method

  1. One problem per email. Pick the single pain that matters most to this persona and write only about that. A second idea halves the reply rate — save it for the follow-up.
  2. Open with a real relevance hook. The first line must prove you're writing to them, not a list — anchored to a trigger they'd recognise (a hire, a launch, a stage change, something they said publicly). No "Hope you're well" or "I came across your profile."
  3. Brevity. Under 90 words, 5 sentences or fewer. It must be readable on a phone lock screen without scrolling. Every sentence earns its place or gets cut.
  4. Single low-friction ask. Ask for interest or a reply, not a 30-minute meeting. "Worth a look?" / "Open to me sharing how?" beats "Do you have 30 mins Tuesday?" The ask is a yes/no, not a calendar negotiation.
  5. No feature-dumping. Name the outcome, not the toolset. One proof point, stated as a customer + result, beats a feature list. Lead with their world, not your product.
  6. Subject-line rules: 2–4 words, lowercase or sentence case, no caps, no emoji, no "Quick question," no "{Company} <> {YourCompany}." Make it look like an internal note from a colleague — reference their problem or trigger, never your product name.

Cold email skeleton:

Subject: <2–4 words, their problem/trigger>

Hi <name>,

<relevance hook tied to a real trigger — proves this isn't a blast>.

<the one problem this persona feels, in their language>.

<one proof point: similar customer + concrete result>.

<single low-friction yes/no ask>?

<first name>

Read the full file on GitHub · 150 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 12d ago First seen · 150 lines · 65 tokens per session scan A 06a70c0fb571

Subscribe to this mod's changes

cold-email is a skill published in the GitHub repository Doris-Labs/sales-skills (3 stars, last pushed 3mo ago), licensed MIT. It adds 65 tokens to every session and 1,467 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.